| { | |
| "best_metric": 0.07050061970949173, | |
| "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold8/checkpoint-70", | |
| "epoch": 4.938271604938271, | |
| "eval_steps": 10, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03950617283950617, | |
| "grad_norm": 0.24279898405075073, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.1922, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.2705923020839691, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.2137, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.31585612893104553, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.2038, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.2717026472091675, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.2181, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.2605282962322235, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.2215, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.25391140580177307, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.155, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.2189364731311798, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.2273, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.2308882772922516, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.1505, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.21543703973293304, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.171, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.21799442172050476, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.1078, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.1351301074028015, | |
| "eval_runtime": 24.0571, | |
| "eval_samples_per_second": 1.871, | |
| "eval_steps_per_second": 1.871, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.22586937248706818, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.1241, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.21821707487106323, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.094, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.17370504140853882, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1207, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.20627069473266602, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.0962, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.21208199858665466, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.0979, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.18776653707027435, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.0993, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.14477351307868958, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1223, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.1340664029121399, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1226, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.131416454911232, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.0999, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.15171606838703156, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1449, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.0886579230427742, | |
| "eval_runtime": 23.95, | |
| "eval_samples_per_second": 1.879, | |
| "eval_steps_per_second": 1.879, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.15347017347812653, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.0717, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.114656463265419, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.0821, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.09925904124975204, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.0777, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.11787675321102142, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.0827, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.11913871020078659, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.092, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.15877272188663483, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.0949, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.10975413024425507, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.048, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.10468373447656631, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1017, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.10285777598619461, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.097, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.11677072197198868, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0376, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.07812924683094025, | |
| "eval_runtime": 23.9589, | |
| "eval_samples_per_second": 1.878, | |
| "eval_steps_per_second": 1.878, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.1213902086019516, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0309, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.11808232963085175, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1121, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.13246725499629974, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0403, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.10101501643657684, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0775, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.08622575551271439, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0869, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.13731761276721954, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0993, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.11113160103559494, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0789, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.10829315334558487, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.0555, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.10348520427942276, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0675, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.11768537014722824, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0743, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.07538121938705444, | |
| "eval_runtime": 23.9623, | |
| "eval_samples_per_second": 1.878, | |
| "eval_steps_per_second": 1.878, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.17533762753009796, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.069, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.09553804248571396, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0707, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.1016172543168068, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0691, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.13637542724609375, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.0952, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.11506781727075577, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0353, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.08644726872444153, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0405, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.14764133095741272, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1304, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.10733048617839813, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0646, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.10831640660762787, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0424, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.08591750264167786, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0667, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.07234559208154678, | |
| "eval_runtime": 23.9773, | |
| "eval_samples_per_second": 1.877, | |
| "eval_steps_per_second": 1.877, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.09558604657649994, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.0498, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.09908287227153778, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0607, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.09224891662597656, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0401, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.11314260214567184, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1218, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.1087903380393982, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.082, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.09997154027223587, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0991, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.11926116049289703, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0829, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.1297048032283783, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0631, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.09436497837305069, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0278, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.09090679883956909, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0539, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.07144327461719513, | |
| "eval_runtime": 23.9577, | |
| "eval_samples_per_second": 1.878, | |
| "eval_steps_per_second": 1.878, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.13741736114025116, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0705, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.09308340400457382, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0435, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.1278102695941925, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0568, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.07728742063045502, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0258, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.10259544104337692, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0517, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.11137136816978455, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0509, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.11223236471414566, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0698, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.1029217466711998, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0407, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.11035247147083282, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0536, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.09024783968925476, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0377, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.07050061970949173, | |
| "eval_runtime": 23.9588, | |
| "eval_samples_per_second": 1.878, | |
| "eval_steps_per_second": 1.878, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.09412938356399536, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0393, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.12862493097782135, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0952, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.10023818910121918, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0537, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.10015217959880829, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0441, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.09044111520051956, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0474, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.1298188865184784, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0826, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.11049933731555939, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0639, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.09569769352674484, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0406, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.10403772443532944, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0567, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.08285118639469147, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.028, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.07062506675720215, | |
| "eval_runtime": 24.0564, | |
| "eval_samples_per_second": 1.871, | |
| "eval_steps_per_second": 1.871, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.11130022257566452, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0646, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.10586877167224884, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0421, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.09351223707199097, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0425, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.11113885790109634, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0441, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.10864410549402237, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0784, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.08787716180086136, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0305, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.09109141677618027, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0283, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.14148326218128204, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.1014, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.10430502146482468, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.038, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.08807569742202759, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0159, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.07075904309749603, | |
| "eval_runtime": 23.9546, | |
| "eval_samples_per_second": 1.879, | |
| "eval_steps_per_second": 1.879, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.09458984434604645, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0324, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.10749012976884842, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0446, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.11104253679513931, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0432, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.14781026542186737, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0707, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.12718258798122406, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0513, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.08762463182210922, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0141, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.1291412115097046, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0584, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.16207610070705414, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0972, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.14718762040138245, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0721, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.09370039403438568, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0299, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.07069163024425507, | |
| "eval_runtime": 23.9654, | |
| "eval_samples_per_second": 1.878, | |
| "eval_steps_per_second": 1.878, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.15139977633953094, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0997, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.1246308982372284, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0705, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.14004313945770264, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0712, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.0948450043797493, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0279, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.11214002221822739, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0474, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.09196820110082626, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0283, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.07508598268032074, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0094, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.09459535777568817, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0157, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.1384902149438858, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0761, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.10075794905424118, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0419, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.07071391493082047, | |
| "eval_runtime": 23.9655, | |
| "eval_samples_per_second": 1.878, | |
| "eval_steps_per_second": 1.878, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.12293389439582825, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0627, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.11310752481222153, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0522, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.12064351886510849, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0523, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.1002722755074501, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0322, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.1027965098619461, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0515, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.10728542506694794, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0442, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.12256431579589844, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0673, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.15612256526947021, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0995, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.10302582383155823, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0306, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.1209910586476326, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0475, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.07094677537679672, | |
| "eval_runtime": 23.9552, | |
| "eval_samples_per_second": 1.879, | |
| "eval_steps_per_second": 1.879, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.10172504186630249, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.01, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.12084975838661194, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0404, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.1270119845867157, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.052, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.10829218477010727, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.047, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.14604143798351288, | |
| "learning_rate": 0.0, | |
| "loss": 0.0846, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.5526893871949414e+17, | |
| "train_loss": 0.07336431298404932, | |
| "train_runtime": 3965.4921, | |
| "train_samples_per_second": 0.511, | |
| "train_steps_per_second": 0.032 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5526893871949414e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |